<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Coding Agent | yuangang.me</title><link>https://yuangang.me/tag/coding-agent/</link><atom:link href="https://yuangang.me/tag/coding-agent/index.xml" rel="self" type="application/rss+xml"/><description>Coding Agent</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 30 Aug 2026 00:00:00 +0000</lastBuildDate><image><url>https://yuangang.me/media/sharing.png</url><title>Coding Agent</title><link>https://yuangang.me/tag/coding-agent/</link></image><item><title>Agents' Last Exam</title><link>https://yuangang.me/publication/agents-last-exam/</link><pubDate>Sun, 30 Aug 2026 00:00:00 +0000</pubDate><guid>https://yuangang.me/publication/agents-last-exam/</guid><description/></item><item><title>Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks</title><link>https://yuangang.me/publication/beyond-output-correctness/</link><pubDate>Tue, 14 Apr 2026 00:00:00 +0000</pubDate><guid>https://yuangang.me/publication/beyond-output-correctness/</guid><description/></item></channel></rss>